Advertisement

Interpretable Deep Learning in Drug Discovery

  • Kristina Preuer
  • Günter Klambauer
  • Friedrich Rippmann
  • Sepp Hochreiter
  • Thomas UnterthinerEmail author
Chapter
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11700)

Abstract

Without any means of interpretation, neural networks that predict molecular properties and bioactivities are merely black boxes. We will unravel these black boxes and will demonstrate approaches to understand the learned representations which are hidden inside these models. We show how single neurons can be interpreted as classifiers which determine the presence or absence of pharmacophore- or toxicophore-like structures, thereby generating new insights and relevant knowledge for chemistry, pharmacology and biochemistry. We further discuss how these novel pharmacophores/toxicophores can be determined from the network by identifying the most relevant components of a compound for the prediction of the network. Additionally, we propose a method which can be used to extract new pharmacophores from a model and will show that these extracted structures are consistent with literature findings. We envision that having access to such interpretable knowledge is a crucial aid in the development and design of new pharmaceutically active molecules, and helps to investigate and understand failures and successes of current methods.

Keywords

Deep learning Neural networks Drug development Target prediction 

References

  1. 1.
    Ancona, M., Ceolini, E., Öztireli, C., Gross, M.: Towards better understanding of gradient-based attribution methods for deep neural networks (2018)Google Scholar
  2. 2.
    Baehrens, D., Schroeter, T., Harmeling, S., Kawanabe, M., Hansen, K., Müller, K.R.: How to explain individual classification decisions. J. Mach. Learn. Res. 11, 1803–1831 (2010). http://dl.acm.org/citation.cfm?id=1756006.1859912MathSciNetzbMATHGoogle Scholar
  3. 3.
    Bau, D., Zhou, B., Khosla, A., Oliva, A., Torralba, A.: Network dissection: quantifying interpretability of deep visual representations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6541–6549 (2017)Google Scholar
  4. 4.
    Bengio, Y.: Deep learning of representations: looking forward. In: Dediu, A.-H., Martín-Vide, C., Mitkov, R., Truthe, B. (eds.) SLSP 2013. LNCS (LNAI), vol. 7978, pp. 1–37. Springer, Heidelberg (2013).  https://doi.org/10.1007/978-3-642-39593-2_1CrossRefGoogle Scholar
  5. 5.
    Cherkasov, A., et al.: QSAR modeling: where have you been? Where are you going to? J. Med. Chem. 57(12), 4977–5010 (2014)CrossRefGoogle Scholar
  6. 6.
    Chollet, F.: Keras (2015). https://keras.io
  7. 7.
    Duvenaud, D.K., et al.: Convolutional networks on graphs for learning molecular fingerprints. In: Cortes, C., Lawrence, N.D., Lee, D.D., Sugiyama, M., Garnett, R. (eds.) Advances in Neural Information Processing Systems 28, pp. 2224–2232. Curran Associates, Inc. (2015)Google Scholar
  8. 8.
    Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O., Dahl, G.E.: Neural message passing for quantum chemistry. In: Precup, D., Teh, Y.W. (eds.) Proceedings of the 34th International Conference on Machine Learning. Proceedings of Machine Learning Research, PMLR, International Convention Centre, Sydney, Australia, vol. 70, pp. 1263–1272, 06–11 August 2017Google Scholar
  9. 9.
    Hansen, K., Baehrens, D., Schroeter, T., Rupp, M., Müller, K.R.: Visual interpretation of kernel-based prediction models. Mol. Inf. 30(9), 817–826 (2011)CrossRefGoogle Scholar
  10. 10.
    Hansen, K., et al.: Benchmark data set for in silico prediction of ames mutagenicity. J. Chem. Inf. Modeling 49(9), 2077–2081 (2009)CrossRefGoogle Scholar
  11. 11.
    Huang, R., et al.: Profiling of the Tox21 10K compound library for agonists and antagonists of the estrogen receptor alpha signaling pathway. Sci. Rep. 4 (2014)Google Scholar
  12. 12.
    Kazius, J., McGuire, R., Bursi, R.: Derivation and validation of toxicophores for mutagenicity prediction. J. Med. Chem. 48(1), 312–320 (2005)CrossRefGoogle Scholar
  13. 13.
    Kearnes, S., McCloskey, K., Berndl, M., Pande, V., Riley, P.: Molecular graph convolutions: moving beyond fingerprints. J. Comput. Aided Mol. Des. 30(8), 595–608 (2016)CrossRefGoogle Scholar
  14. 14.
    Klambauer, G., Unterthiner, T., Mayr, A., Hochreiter, S.: Self-normalizing neural networks. In: Advances in Neural Information Processing Systems 30 (NIPS) (2017)Google Scholar
  15. 15.
    Lavecchia, A.: Machine-learning approaches in drug discovery: methods and applications. Drug Discovery Today 20(3), 318–331 (2015)CrossRefGoogle Scholar
  16. 16.
    Lin, S.: Pharmacophore perception, development and use in drug design. Edited by Osman F. Güner. Molecules 5(7), 987–989 (2000)CrossRefGoogle Scholar
  17. 17.
    Lionta, E., Spyrou, G., Vassilatis, D.K., Cournia, Z.: Structure-based virtual screening for drug discovery: principles, applications and recent advances. Curr. Top. Med. Chem. 14(16), 1923–1938 (2014)CrossRefGoogle Scholar
  18. 18.
    Lounkine, E., et al.: Large-scale prediction and testing of drug activity on side-effect targets. Nature 486(7403), 361–367 (2012).  https://doi.org/10.1038/nature11159CrossRefGoogle Scholar
  19. 19.
    Ma, J., Sheridan, R.P., Liaw, A., Dahl, G.E., Svetnik, V.: Deep neural nets as a method for quantitative structure-activity relationships. J. Chem. Inf. Model. 55(2), 263–274 (2015)CrossRefGoogle Scholar
  20. 20.
    Mayr, A., Klambauer, G., Unterthiner, T., Hochreiter, S.: DeepTox: toxicity prediction using deep learning. Frontiers Environ. Sci. 3, 80 (2016)CrossRefGoogle Scholar
  21. 21.
    Mayr, A., et al.: Large-scale comparison of machine learning methods for drug target prediction on ChEMBL. Chem. Sci. 9(24), 5441–5451 (2018)CrossRefGoogle Scholar
  22. 22.
    Olivecrona, M., Blaschke, T., Engkvist, O., Chen, H.: Molecular de-novo design through deep reinforcement learning. J. Cheminform. 9(1), 48 (2017)CrossRefGoogle Scholar
  23. 23.
    Plošnik, A., Vračko, M., Dolenc, M.S.: Mutagenic and carcinogenic structural alerts and their mechanisms of action. Arch. Ind. Hyg. Toxicol. 67(3), 169–182 (2016)Google Scholar
  24. 24.
    Preuer, K., Lewis, R.P.I., Hochreiter, S., Bender, A., Bulusu, K.C., Klambauer, G.: DeepSynergy: predicting anti-cancer drug synergy with deep learning. Bioinformatics 34(9), 1538–1546 (2017)CrossRefGoogle Scholar
  25. 25.
    Preuer, K., Renz, P., Unterthiner, T., Hochreiter, S., Klambauer, G.: Fréchet ChemNet distance: a metric for generative models for molecules in drug discovery. J. Chem. Inf. Model. 58(9), 1736–1741 (2018)CrossRefGoogle Scholar
  26. 26.
    Rogers, D., Hahn, M.: Extended-connectivity fingerprints. J. Chem. Inf. Model. 50(5), 742–754 (2010)CrossRefGoogle Scholar
  27. 27.
    Schütt, K.T., Arbabzadah, F., Chmiela, S., Müller, K.R., Tkatchenko, A.: Quantum-chemical insights from deep tensor neural networks. Nat. Commun. 8, 13890 (2017)CrossRefGoogle Scholar
  28. 28.
    Segler, M.H., Kogej, T., Tyrchan, C., Waller, M.P.: Generating focused molecule libraries for drug discovery with recurrent neural networks. ACS Central Sci. (2017)Google Scholar
  29. 29.
    Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. In: Proceedings of the 34th International Conference on Machine Learning (ICML) (2017)Google Scholar
  30. 30.
    Sushko, I., Salmina, E., Potemkin, V.A., Poda, G., Tetko, I.V.: ToxAlerts: a web server of structural alerts for toxic chemicals and compounds with potential adverse reactions. J. Chem. Inf. Model. 52(8), 2310–2316 (2012)CrossRefGoogle Scholar
  31. 31.
    Unterthiner, T., et al.: Multi-task deep networks for drug target prediction. In: Workshop on Transfer and Multi-task Learning of NIPS 2014, vol. 2014, pp. 1–4 (2014)Google Scholar
  32. 32.
    Unterthiner, T., et al.: Deep learning as an opportunity in virtual screening. In: Deep Learning and Representation Learning Workshop (NIPS 2014) (2014)Google Scholar
  33. 33.
    Unterthiner, T., Nessler, B., Klambauer, G., Heusel, M., Ramsauer, H., Hochreiter, S.: Coulomb GANs: provably optimal Nash equilibria viapotential fields. In: International Conference of Learning Representations (ICLR) (2018)Google Scholar
  34. 34.
    Yang, H., Li, J., Wu, Z., Li, W., Liu, G., Tang, Y.: Evaluation of different methods for identification of structural alerts using chemical ames mutagenicity data set as a benchmark. Chem. Res. Toxicol. 30(6), 1355–1364 (2017)CrossRefGoogle Scholar
  35. 35.
    Yang, X., Zhang, J., Yoshizoe, K., Terayama, K., Tsuda, K.: ChemTS: an efficient python library for de novo molecular generation. Sci. Technol. Adv. Mater. 18(1), 972–976 (2017)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Kristina Preuer
    • 1
  • Günter Klambauer
    • 1
  • Friedrich Rippmann
    • 2
  • Sepp Hochreiter
    • 1
  • Thomas Unterthiner
    • 1
    Email author
  1. 1.Johannes Kepler University LinzLinzAustria
  2. 2.Computational Chemistry and BiologyMerck KGaADarmstadtGermany

Personalised recommendations